Training datasets for AIMNet2 machine-learned neural network potential

The datasets contain molecular structures and the properties computed with B97-3c (GGA DFT) or wB97M-def2-TZVPP (range-separated hybrid DFT) methods. Each data file contains about 20M structures. DFT calculation performed with ORCA 5.0.3 software. Properties include energy, forces, atomic charges, and molecular dipole and quadrupole moments.

本数据集收录了采用B97-3c (GGA DFT) 或 wB97M-def2-TZVPP (范围分离混合密度泛函理论) 方法计算得到的分子结构及其相关性质。每个数据文件包含大约20MB的分子结构。DFT计算使用ORCA 5.0.3软件完成。性质数据包括能量、力、原子电荷以及分子的偶极矩和四极矩。